xflr6

xflr6

"""Compare feed enclosure length with content-length of file url."""

import urllib.request
import xml.etree.ElementTree as etree

URL = 'https://feeds.feedburner.com/thebuglefeed?format=xml'


with urllib.request.urlopen(URL) as f:
    tree = etree.parse(f)

xflr6

"""SQL-injection safe dynamic query with pl/pgsql."""

import sqlalchemy as sa

UNIQUE_NULL = [('contributioncontributor', ['contribution_pk', 'contributor_pk'], []),
               ('contributionreference', ['contribution_pk', 'source_pk', 'description'], []),
               ('editor', ['dataset_pk', 'contributor_pk'], []),
               ('languageidentifier', ['language_pk', 'identifier_pk'], []),
               ('languagesource', ['language_pk', 'source_pk'], []),
               ('sentencereference', ['sentence_pk', 'source_pk', 'description'], []),

xflr6

"""Longest common prefix."""

import itertools


def common_prefix(left: str, right: str) -> str:
    """Return the case-insensitive longest common prefix of two strings.

    >>> common_prefix('spam', 'spameggs')
    'spam'

xflr6

"""Combine https://glottolog.org/langdoc.csv parts."""

import urllib.parse

import pandas as pd

ENDPOINT = urllib.parse.urlparse('https://glottolog.org/langdoc.csv')

QUERY = {'sEcho': 1,
         'iSortingCols': 1,

xflr6

"""Dump basic https://glottolog.org languoid info to CSV file."""

import pandas as pd

ENGINE = 'postgresql://postgres@/glottolog3'

QUERY = '''
SELECT
  l.id AS glottocode,
  l.name,

xflr6

xflr6

xflr6

xflr6

"""Build RDF with rdflib and serialize in turtle format."""

import rdflib
from rdflib.namespace import DCTERMS, RDF, RDFS, SKOS

GOLD = rdflib.Namespace('http://purl.org/linguistics/gold/')

LANGUOID = rdflib.Namespace('http://glottolog.org/resource/languoid/id/')

VOID = rdflib.Namespace('http://rdfs.org/ns/void#')